Zobrazeno 1 - 10
of 271
pro vyhledávání: '"Guangyou Xu"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 31:1817-1830
Elastic motion is a nonrigid motion constrained only by some degree of smoothness and continuity. Consequently, elastic motion estimation by explicit feature matching actually contains two correlated subproblems: shape registration and motion trackin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c0588241f5b5937768093c8a8a64a97c
https://doi.org/10.1109/tpami.2009.111
https://doi.org/10.1109/tpami.2009.111
Publikováno v:
Tsinghua Science and Technology. 12:44-50
An algorithm is presented for estimating the direction and strength of point light with the strength of ambient illumination. Existing approaches evaluate these illumination parameters directly in the high dimensional image space, while we estimate t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fe11828af2eccd5c88ca7edbf8664792
https://doi.org/10.1016/s1007-0214(07)70007-x
https://doi.org/10.1016/s1007-0214(07)70007-x
Autor:
Yanghua Liu, Guangyou Xu
Publikováno v:
Tsinghua Science and Technology. 12:51-57
Realistic personalized face animation mainly depends on a picture-perfect appearance and natural head rotation. This paper describes a face model for generation of novel view facial textures with various realistic expressions and poses. The model is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::becf4108581adcecd3736959fb002954
https://doi.org/10.1016/s1007-0214(07)70008-1
https://doi.org/10.1016/s1007-0214(07)70008-1
Publikováno v:
Intelligent Computing Theories and Methodologies ISBN: 9783319221854
ICIC (2)
ICIC (2)
This paper proposes a novel probabilistic graphical model, called MTHMM-P, for partitioning general nonrigid motion into piecewise elastic motion, so as to achieve nonrigid motion estimation without the need of any a priori shape model. To this end,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6ba9530e79952ba9da9281e5730370e
https://doi.org/10.1007/978-3-319-22186-1_21
https://doi.org/10.1007/978-3-319-22186-1_21
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319219684
ICIG (3)
ICIG (3)
In traditional contour tracker, object’s location and shape are usually bound together to form the system state. Such approaches suffer from the problem that most sampled states cannot match the object’s boundary exactly when the boundary cannot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b0ca947aac073be699ae41d8be21c48f
https://doi.org/10.1007/978-3-319-21969-1_21
https://doi.org/10.1007/978-3-319-21969-1_21
Publikováno v:
Chinese Science Bulletin. 51:121-128
With the rapid development of computer, communication, and sensing technology, our living space has been transformed from physical space into a space shared by physical space and cyberspace. In the light of this fact and based on analyzing the char-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8bebbab06191f375c831f0f3fd0d0dad
https://doi.org/10.1007/s11434-004-0643-y
https://doi.org/10.1007/s11434-004-0643-y
Publikováno v:
Image and Vision Computing. 24:13-26
This paper presents a unified approach to automatically build dynamic and multi-resolution 360^o panoramic (DMP) representations from image sequences captured by hand-held cameras mainly undertaking rotation and zooming for natural scenes with moving
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c39b686140259b30ddc1ea73388d02d7
https://doi.org/10.1016/j.imavis.2005.09.006
https://doi.org/10.1016/j.imavis.2005.09.006
Publikováno v:
Pattern Recognition. 38:865-885
Multi-level annotation of images is a promising solution to enable semantic image retrieval by using various keywords at different semantic levels. In this paper, we propose a multi-level approach to interpret and annotate the semantics of natural im
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c2778d14760efcb54578dbd3734b3e9
https://doi.org/10.1016/j.patcog.2004.07.011
https://doi.org/10.1016/j.patcog.2004.07.011
Publikováno v:
International Journal of Computer Vision. 61:1-26
This paper presents a Fourier-based approach for automatically constructing a 3D panoramic model of a natural scene from a video sequence. The video sequences could be captured by an unstabilized camera mounted on a moving platform on a common road s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b1aa2300b1aa613875b7b15f9627148
https://doi.org/10.1023/b:visi.0000045325.10439.3f
https://doi.org/10.1023/b:visi.0000045325.10439.3f
Publikováno v:
Journal of Computer Science and Technology. 19:489-500
This paper describes a novel method for tracking complex non-rigid motions by learning the intrinsic object structure. The approach builds on and extends the studies on non-linear dimensionality reduction for object representation, object dynamics mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0558ba6d5f942c0b585ebb23e47fc781
https://doi.org/10.1007/bf02944750
https://doi.org/10.1007/bf02944750